paper-with-me

홈 › Papers

DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering

2026-03-10 · Tong Wang, Chi Jin, Yongkang Chen, Huan Deng, Xiaohui Kuang, Gang Zhao arxiv

Table Question Answering (TableQA) enables natural language interaction with structured tabular data. However, existing large language model (LLM) approaches face critical limitations: context length constraints that restrict data handling capabilities, hallucination issues that compromise answer reliability, and single-agent architectures that struggle with complex reasoning scenarios involving semantic relationships and multi-hop logic. This paper introduces DataFactory, a multi-agent framework that addresses these limitations through specialized team coordination and automated knowledge transformation. The framework comprises a Data Leader employing the ReAct paradigm for reasoning orchestration, together with dedicated Database and Knowledge Graph teams, enabling the systematic decomposition of complex queries into structured and relational reasoning tasks. We formalize automated data-to-knowledge graph transformation via the mapping function T:D x S x R -> G, and implement natural language-based consultation that - unlike fixed workflow multi-agent systems - enables flexible inter-agent deliberation and adaptive planning to improve coordination robustness. We also apply context engineering strategies that integrate historical patterns and domain knowledge to reduce hallucinations and improve query accuracy. Across TabFact, WikiTableQuestions, and FeTaQA, using eight LLMs from five providers, results show consistent gains. Our approach improves accuracy by 20.2% (TabFact) and 23.9% (WikiTQ) over baselines, with significant effects (Cohen's d > 1). Team coordination also outperforms single-team variants (+5.5% TabFact, +14.4% WikiTQ, +17.1% FeTaQA ROUGE-2). The framework offers design guidelines for multi-agent collaboration and a practical platform for enterprise data analysis through integrated structured querying and graph-based knowledge representation.

📄 PDF Abstract BibTeX arXiv:2603.09152

Code (0)

등록된 구현이 없습니다.

Tasks

Relational ReasoningQuestion Answering

Similar Papers 제목 키워드 기반

Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge

2026-01-26 · Li Kang, Heng Zhou, Xiufeng Song, Rui Li 외 arxiv

Recent advancements in multimodal large language models and vision-languageaction models have significantly driven progress in Embodied AI. As the field transitions toward more complex task scenarios, multi-agent system …

Multi-Agent Collaborative Framework For Math Problem Generation

2025-11-06 · Kia Karbasi, Kevin Hong, Mohammad Amin Samadi, Gregory Pottie arxiv

Automatic question generation (AQG) for mathematics education remains an elusive goal for Intelligent Tutoring Systems and educators. While pre-trained transformer-based language models have significantly advanced natura…

Question Generation

SensingAgents: A Multi-Agent Collaborative Framework for Robust IMU Activity Recognition

2026-05-06 · Naiyu Zheng, Tianlong Yu, Haochen Yin, Xiaoyi Fan 외 arxiv

Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is a cornerstone of mobile health, smart environments, and human-computer interaction. However, current deep learning-based HAR models often …

Human Activity Recognition

AgenticAD: A Specialized Multiagent System Framework for Holistic Alzheimer Disease Management

2025-09-01 · Adib Bazgir, Amir Habibdoust, Xing Song, Yuwen Zhang arxiv

Alzheimer's disease (AD) presents a complex, multifaceted challenge to patients, caregivers, and the healthcare system, necessitating integrated and dynamic support solutions. While artificial intelligence (AI) offers pr…

CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models

2024-04-02 · Xuechen Liang, Yangfan He, Meiling Tao, Yinghui Xia 외

Open large language models (LLMs) have significantly advanced the field of natural language processing, showcasing impressive performance across various tasks.Despite the significant advancements in LLMs, their effective…